Systems and techniques for a mechanism for conflict resolution and avoidance of collisions for highly automated and autonomous vehicles are described herein. In an example, a gesture resolution system of an autonomous vehicle is adapted to detect, using input received from a camera, a moving object near the autonomous vehicle. The gesture resolution system may be further adapted to determine the moving object presents a risk of collision with the autonomous vehicle. The gesture resolution system may be further adapted to detect a gesture performed by the moving object. The gesture resolution system may be further adapted to determine a meaning of the gesture. The gesture resolution system may be further adapted to display, in a graphical user interface, the meaning for the gesture and an interface element to override the meaning of the gesture.
Legal claims defining the scope of protection, as filed with the USPTO.
1. A system for gesture resolution with an autonomous vehicle, comprising: at least one processor; and memory including instructions that, when executed by the at least one processor, cause the at least one processor to: detect, using input received from a camera, a moving object in an environment exterior to the autonomous vehicle; determine the moving object presents a safety risk with the autonomous vehicle; in response to determining the safety risk with the moving object, detect a gesture performed by the moving object; determine, using a trained gesture interpretation model, a response to the gesture; provide a user input option, via a graphical user interface within the autonomous vehicle, for a passenger to override an interpretation of the gesture or override an intended action of the vehicle in response to the gesture, the user interface displaying a meaning for the interpretation of gesture, wherein training of a gesture interpretation model is based on inputs of gesture data and selection from the user input option; and execute a command for the autonomous vehicle based on the determined response to the gesture.
2. The system of claim 1 , further comprising instructions to determine the moving object presents a risk of collision, including instructions to: calculate a risk assessment value; and determine the risk assessment value exceeds a predetermined threshold.
3. The system of claim 2 , wherein to calculate the risk assessment value, further comprising instructions to: calculate vectors of motion for the moving object; calculate vectors of motion for the autonomous vehicle; and determine, based on the vectors of motion for the moving object and vectors of motion for the autonomous vehicle, a probability of collision between the autonomous vehicle and the moving object.
4. The system of claim 2 , wherein the risk assessment value is based on the distance between the moving object and the autonomous vehicle.
5. The system of claim 2 , wherein the risk assessment value is based on identifying the type of moving object.
6. The system of claim 1 , wherein user input received via the graphical user interface causes the autonomous vehicle to stop current movements.
7. The system of claim 1 , further comprising instructions to: receive an override indication for the interpretation of the gesture from the graphical user interface; receive input describing a new interpretation of the gesture; and store the gesture and the new interpretation of the gesture.
8. A method for gesture resolution with an autonomous vehicle, comprising: detecting, using input received from a camera, a moving object in an environment exterior to the autonomous vehicle; determining the moving object presents a safety risk with the autonomous vehicle; in response to determining the safety risk with the moving object, detecting a gesture performed by the moving object; determining, using a trained gesture interpretation model, a response to the gesture; providing a user input option, via a graphical user interface within the autonomous vehicle, for a passenger to override an interpretation of the gesture or override an intended action of the vehicle in response to the gesture, the user interface displaying a meaning for the interpretation of gesture, wherein training of a gesture interpretation model is based on inputs of gesture data and selection from the user input option; and execute a command for the autonomous vehicle based on the determined response to the gesture.
9. The method of claim 8 , further comprising determining the moving object presents a risk of collision, comprising: calculating a risk assessment value; and determining the risk assessment value exceeds a predetermined threshold.
10. The method of claim 9 , wherein to calculate the risk assessment value, further comprising: calculating vectors of motion for the moving object; calculating vectors of motion for the autonomous vehicle; and determining, based on the vectors of motion for the moving object and vectors of motion for the autonomous vehicle, a probability of collision between the autonomous vehicle and the moving object.
11. The method of claim 9 , wherein the risk assessment value is based on the distance between the moving object and the autonomous vehicle.
12. The method of claim 9 , wherein the risk assessment value is based on identifying the type of moving object.
13. The method of claim 8 , wherein user input received via the graphical user interface causes the autonomous vehicle to stop current movements.
14. The method of claim 8 , further comprising: receiving an override indication for the interpretation of the gesture from the graphical user interface; receiving input describing a new interpretation of the gesture; and storing the gesture and the new interpretation of the gesture.
15. At least one non-transitory computer readable medium including instructions for gesture resolution with an autonomous vehicle that when executed by at least one processor, cause the at least one processor to: detect, using input received from a camera, a moving object in an environment exterior to the autonomous vehicle; determine the moving object presents a safety risk with the autonomous vehicle; in response to determining the safety risk with the moving object, detect a gesture performed by the moving object; determine, using a trained gesture interpretation model, a response to the gesture; provide a user input option, via a graphical user interface within the autonomous vehicle, for a passenger to override an interpretation of the gesture or override an intended action of the vehicle in response to the gesture, the user interface displaying a meaning for the interpretation of gesture, wherein training of a gesture interpretation model is based on inputs of gesture data and selection from the user input option; and execute a command for the autonomous vehicle based on the determined response to the gesture.
16. The at least one non-transitory computer readable medium of claim 15 , further comprising instructions to determine the moving object presents a risk of collision, including instructions to: calculate a risk assessment value; and determine the risk assessment value exceeds a predetermined threshold.
17. The at least one non-transitory computer readable medium of claim 16 , wherein to calculate the risk assessment value, further comprising instructions to: calculate vectors of motion for the moving object; calculate vectors of motion for the autonomous vehicle; and determine, based on the vectors of motion for the moving object and vectors of motion for the autonomous vehicle, a probability of collision between the autonomous vehicle and the moving object.
18. The at least one non-transitory computer readable medium of claim 16 , wherein the risk assessment value is based on the distance between the moving object and the autonomous vehicle.
19. The at least one non-transitory computer readable medium of claim 16 , wherein the risk assessment value is based on identifying the type of moving object.
20. The at least one non-transitory computer readable medium of claim 15 , wherein user input received via the graphical user interface causes the autonomous vehicle to stop current movements.
21. The at least one non-transitory computer readable medium of claim 15 , further comprising instructions to: receive an override indication for the interpretation of the gesture from the graphical user interface; receive input describing a new interpretation of the gesture; and store the gesture and the new interpretation of the gesture.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
February 5, 2019
May 31, 2022
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.